Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!mips!spool.mu.edu!snorkelwacker.mit.edu!bloom-beacon!eru!hagbard!sunic!mcsun!ukc!edcastle!cs.ed.ac.uk!arshad
From: arshad@cs.ed.ac.uk (Arshad Mahmood)
Newsgroups: comp.ai.neural-nets
Subject: Neural Network applications to Law
Message-ID: <8754@skye.cs.ed.ac.uk>
Date: 11 Apr 91 19:29:18 GMT
References: <25154.671325056@hplpm.hpl.hp.com>
Sender: nnews@cs.ed.ac.uk
Reply-To: arshad@lfcs.ed.ac.uk (Arshad Mahmood)
Organization: Laboratory for the Foundations of Computer Science, Edinburgh U
Lines: 28

Could anybody refer me to any references which apply neural network techniques
to law. There is at present a major initiative (both within Britian and 
elsewhere) to apply techniques from computer science to law (this can
range from as an aid to teaching to the actual use of expert systems in
arriving at suitable statuates, etc).

The problem with most common approaches is that they require a rather rigid
area (such as taxation, or immigration) which although being very complex
is however relatively routine to actually apply. This is sadly not
so with the majority of law, and consequently techniques ranging from
logic programming to expert systems are being investigated.

It appears to me however that the Anderson/Hinton Associative Memory research
would be a great step forward in most of these other areas. We accept that we
are in this regard taking a very positivistic view of law, but since this is 
the way law is commonly taught it doesn't seem unduly harmful at present.

I am not a lawyer, therefore this is for a friend who on my advice has taken
up at looking into connectionist approaches. We were however not aware of
any specific work on this and would be most happy to hear of any relevent
work.

Regards,

A. Mahmood
LFCS
Edinburgh University
Scotland